From 3685afda47fa0d11d0edf43c6161cef690bae461 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 20 七月 2023 20:40:02 +0800
Subject: [PATCH] bugfix long wav

---
 funasr/bin/asr_inference_launch.py |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 7ddacf0..36c6d76 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -565,6 +565,7 @@
         if 'hotword' in kwargs:
             hotword_list_or_file = kwargs['hotword']
 
+        speech2vadsegment.vad_model.vad_opts.max_single_segment_time = kwargs.get("max_single_segment_time", 60000)
         batch_size_token = kwargs.get("batch_size_token", 6000)
         print("batch_size_token: ", batch_size_token)
 
@@ -647,8 +648,7 @@
             beg_idx = 0
             for j, _ in enumerate(range(0, n)):
                 batch_size_token_ms_cum += (sorted_data[j][0][1] - sorted_data[j][0][0])
-                if j < n - 1 and (batch_size_token_ms_cum + sorted_data[j + 1][0][1] - sorted_data[j + 1][0][
-                    0]) < batch_size_token_ms:
+                if j < n - 1 and (batch_size_token_ms_cum + sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size_token_ms and (sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < speech2vadsegment.vad_model.vad_opts.max_single_segment_time:
                     continue
                 batch_size_token_ms_cum = 0
                 end_idx = j + 1

--
Gitblit v1.9.1